spec-shaping

spec-shaping is a skill for Claude Code, Codex from nweii/agent-stuff. It costs 38 tokens per session (1,726 once invoked), scanned A, original, MIT.

A skill for turning rough product ideas or existing specifications into focused product specifications and sprint plans. A sprint is a short, defined period of development work.

In plain words
What is it for?
It is for interviewing about an idea, scoping product work, breaking specifications into tasks and sprints, and maintaining the related documents.
Why use it?
It helps resolve unclear goals and divide large ideas into smaller pieces that can be built and demonstrated.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nweii/agent-stuff/spec-shaping
Any agent
npx skills add nweii/agent-stuff --skill spec-shaping
Clone the repo
git clone --depth 1 https://github.com/nweii/agent-stuff

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for spec-shaping

README.md
[![agentmods](https://agentmods.dev/badge/skills/nweii/agent-stuff/spec-shaping.svg)](https://agentmods.dev/skills/nweii/agent-stuff/spec-shaping)
Your own site
<a href="https://agentmods.dev/skills/nweii/agent-stuff/spec-shaping"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/spec-shaping.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.01726
Opus 5 $0.00019 $0.00863
Sonnet 5 $0.00008 $0.00345
Haiku 4.5 $0.00004 $0.00173

Measured 2d ago against content hash d9d809581ecf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

spec-shaping scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/spec-shaping/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Shaping

Transform product ideas into well-scoped specs and actionable sprint plans. This skill supports two complementary modes:

  1. Interview mode: Probe the problem space until a clear, narrow spec emerges
  2. Sprint breakdown mode: Decompose a spec into atomic tasks and demoable sprints

When to Use

  • User has a rough product plan or idea that needs scoping
  • User needs help thinking through implementation details, UI/UX, or tradeoffs
  • User has a spec ready to break into sprints and tasks
  • User wants to validate whether a problem is well-framed before building

Document Management

Treat specs and sprint plans as living documents. Use the following standards to ensure consistency and "freshness".

1. File Operations (Search, Location, Updates)

  • Search First: Before creating a new file, search for existing specs for this project.
  • Update vs. New:
    • Update: If the "Identity" of the project is the same (same core problem, just refining/pivoting implementation), update the existing spec.
      • Action: Rename file to today's date + update Metadata.
    • New: If the problem definition has fundamentally changed, or the solution direction is a complete "burn it down" restart, create a new spec.
  • Output Location (Adaptive):
    1. Scan for: specs/, planning/, docs/specs/, product/.
    2. If found: Use that directory.
    3. Default: Create and use specs/.
    4. Vaults: If external, check agents.md/claude.md for overrides.

2. File Standards (Naming, Metadata, Content)

  • Naming: [Semantic name] - [YYYY-MM-DD].md
    • Specs: Checkout flow spec - 2024-03-25.md
    • Sprints: Checkout flow sprints - 2024-03-25.md
  • Frontmatter:
    ---
    status: [Planned | In Progress | Completed]
    last: [YYYY-MM-DD]
    ---
    
  • Context Header (Required):
    > [!NOTE] > **Context**: [Why was this updated? e.g. "Pivot to V2"] > _This document reflects the product thinking at the time of the last update._
    
  • Changelog: Keep a ## Changelog at the bottom. Initialize if missing. Only log significant changes (e.g. scope pivots). Ignore trivial edits.

Read the full file on GitHub · 138 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 138 lines · 38 tokens per session scan A d9d809581ecf

Subscribe to this mod's changes

spec-shaping is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 14d ago), licensed MIT. It adds 38 tokens to every session and 1,726 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens